Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to emphasizing or drawing attention to specific information or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens related to "highlighting"

    np_acts-logits-general · gemini-2.0-flash

    highlighting specific points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.60
    principalColumn
    -0.60
    SharedDtor
    -0.55
     informée
    -0.50
     RequestMethod
    -0.49
     tubeless
    -0.45
    ctrons
    -0.44
     Mesin
    -0.43
     Савезне
    -0.42
    Biografie
    -0.42
    POSITIVE LOGITS
     highlight
    1.15
     highlighting
    1.13
     Highlight
    1.08
     highlights
    1.07
     highlighted
    1.04
    highlight
    1.03
     emphasize
    1.03
     emphasized
    1.02
     emphasizes
    1.02
    Highlight
    0.96
    Act Density 0.152%

    No Known Activations